Ultrasound Image Segmentation in Cardiovascular Disease: A Review of Techniques and Clinical Applications

Abstract

This review provides a comprehensive overview of echocardiographic image segmentation techniques in representative clinical contexts, including valvular heart disease (VHD), congenital heart disease (CHD), and left ventricular (LV) dysfunction and heart failure. The article first outlines the standardized workflow for ultrasound (US) image segmentation, establishing a technical framework for comparing and evaluating different approaches. This is followed by a brief overview of the pathophysiological characteristics of these conditions, highlighting their anatomical segmentation requirements and clinical implications. Subsequently, the review summarizes the evolution and key contributions of traditional image processing, machine learning (ML), and deep learning (DL) methods across different disease types. Comparative analysis indicates that DL models, with their end-to-end training strategies and hierarchical feature representation, demonstrate substantial advantages in segmentation automation and accuracy. Finally, the article discusses current challenges in data acquisition, model generalizability, and clinical integration, and explores future research directions to promote the development and translational application of intelligent echocardiographic analysis.